|
--- |
|
library_name: transformers |
|
license: other |
|
base_model: Qwen/Qwen2.5-1.5B-Instruct |
|
tags: |
|
- llama-factory |
|
- full |
|
- generated_from_trainer |
|
model-index: |
|
- name: MATH_training_response_Qwen2.5_1.5B_only_right |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# MATH_training_response_Qwen2.5_1.5B_only_right |
|
|
|
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the MATH_training_response_Qwen2.5_1.5B_only_right dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0696 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- total_train_batch_size: 8 |
|
- total_eval_batch_size: 4 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.0714 | 0.4090 | 200 | 0.0944 | |
|
| 0.0896 | 0.8180 | 400 | 0.0866 | |
|
| 0.029 | 1.2270 | 600 | 0.0771 | |
|
| 0.0247 | 1.6360 | 800 | 0.0706 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.1 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
